Saptarshi Sengupta

Saptarshi7's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 14 days ago

Running

94

The Eiffel Tower Llama

📝

94

Explore the Eiffel Tower Llama experiment with open-source models

New activity in Qwen/Qwen3-32B about 1 month ago

Qwen3ForCausalLM - Architecture issue

2

#26 opened 8 months ago by

cr-gkn

authored a paper about 2 months ago

ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers

Paper • 2510.19791 • Published Oct 22, 2025

New activity in Kingsoft-LLM/QZhou-Embedding 3 months ago

Issue running model with Sentence Transformers

13

#3 opened 3 months ago by

Saptarshi7

Issue with running on latest libraries - Fix Provided

#2 opened 3 months ago by

Saptarshi7

New activity in nvidia/NV-Embed-v2 3 months ago

error in latest transformers 4.56.0, AttributeError: 'DynamicCache' object has no attribute 'get_usable_length'. Did you mean: 'get_seq_length'

5

#45 opened 5 months ago by

le723z

authored a paper 4 months ago

BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

Paper • 2506.05766 • Published Jun 6, 2025

updated a dataset 4 months ago

BioMolMQA/BioMolMQA

Viewer • Updated Sep 6, 2025 • 1.68k • 105

updated a dataset 7 months ago

Saptarshi7/covid_qa_cleaned_CS

Updated Jun 11, 2025 • 75

published a dataset 9 months ago

BioMolMQA/BioMolMQA

Viewer • Updated Sep 6, 2025 • 1.68k • 105

authored 4 papers 10 months ago

TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering

Paper • 2310.16995 • Published Oct 25, 2023

Exploring Language Model Generalization in Low-Resource Extractive QA

Paper • 2409.18446 • Published Sep 27, 2024

MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification

Paper • 2412.04494 • Published Nov 28, 2024

Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings

Paper • 2401.07977 • Published Jan 15, 2024

New activity in tiiuae/falcon-7b over 2 years ago

Trying to understand internals of falcon

1

#46 opened over 2 years ago by

MorphzZ

Question answering task with falcon model fails with "TypeError: forward() got an unexpected keyword argument 'token_type_ids'"

1

#75 opened over 2 years ago by

karolzak13

New activity in facebook/galactica-30b over 2 years ago

KeyError

👍 3

16

#4 opened about 3 years ago by

lukaemon

New activity in studio-ousia/luke-base over 2 years ago

CUDA error when trying to Pre-Train

6

#4 opened over 2 years ago by

Saptarshi7

New activity in studio-ousia/luke-base almost 3 years ago

Tokenizer Issue

2

#2 opened almost 3 years ago by

Saptarshi7

New activity in GanjinZero/UMLSBert_ENG almost 3 years ago

🚩 Report

3

#1 opened almost 3 years ago by

Saptarshi7